Zelknight463 commited on
Commit
c8d1a51
1 Parent(s): c2b4ca1

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - OpenPipe/mistral-ft-optimized-1218
4
+ - mlabonne/NeuralHermes-2.5-Mistral-7B
5
+ tags:
6
+ - merge
7
+ - mergekit
8
+ - lazymergekit
9
+ - OpenPipe/mistral-ft-optimized-1218
10
+ - mlabonne/NeuralHermes-2.5-Mistral-7B
11
+ ---
12
+
13
+ # NeuralPipe-9B-merged
14
+
15
+ NeuralPipe-9B-merged is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
16
+ * [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
17
+ * [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
18
+
19
+ ## 🧩 Configuration
20
+
21
+ ```yaml
22
+ slices:
23
+ - sources:
24
+ - model: OpenPipe/mistral-ft-optimized-1218
25
+ layer_range: [0, 32]
26
+ - sources:
27
+ - model: mlabonne/NeuralHermes-2.5-Mistral-7B
28
+ layer_range: [24, 32]
29
+ merge_method: passthrough
30
+ dtype: bfloat16
31
+ ```
32
+
33
+ ## 💻 Usage
34
+
35
+ ```python
36
+ !pip install -qU transformers accelerate
37
+
38
+ from transformers import AutoTokenizer
39
+ import transformers
40
+ import torch
41
+
42
+ model = "Zelknight463/NeuralPipe-9B-merged"
43
+ messages = [{"role": "user", "content": "What is a large language model?"}]
44
+
45
+ tokenizer = AutoTokenizer.from_pretrained(model)
46
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
47
+ pipeline = transformers.pipeline(
48
+ "text-generation",
49
+ model=model,
50
+ torch_dtype=torch.float16,
51
+ device_map="auto",
52
+ )
53
+
54
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
55
+ print(outputs[0]["generated_text"])
56
+ ```
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mlabonne/NeuralHermes-2.5-Mistral-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.42.3",
24
+ "use_cache": false,
25
+ "vocab_size": 32002
26
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ slices:
3
+ - sources:
4
+ - model: OpenPipe/mistral-ft-optimized-1218
5
+ layer_range: [0, 32]
6
+ - sources:
7
+ - model: mlabonne/NeuralHermes-2.5-Mistral-7B
8
+ layer_range: [24, 32]
9
+ merge_method: passthrough
10
+ dtype: bfloat16
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0527479ebbfad409bf4d9dcfcd7903d2949c1afaae4118e15e4c697d2793592
3
+ size 960537936
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:011177536933a99f03b42a229f6983be01f522b1da89001271af6e367833d19f
3
+ size 989890720
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f365f6889b984a15fc7f55b74aaf967b4bfa6be69cb426e7600878fbc7f9c084
3
+ size 989890728
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba951e56b1e67db3272dc6e458a610772604721575c99d39b333c44ecd0819a
3
+ size 998287760
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd23daff3c0350e3012f6d9b48829f50f24b06e561fa68163919833ac588583b
3
+ size 947956216
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89270274e63f76c665b91d02c3bcd02706063affc07857bbe0ba53ff24ad33ab
3
+ size 989890728
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f19ea64d876c658fb563642d9b3f5f23928ad6848b3bd85866fd5757aa29325
3
+ size 989890720
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad3d7b468b78895eee3aa52ef85e274b79e52cd02d357cd77f1fef860aa8310
3
+ size 998287760
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92533e61468fd3b971d2ddd999dcf99a0fd8ad39c53d5f300005af6dbe354548
3
+ size 947964520
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d4f09dd7c7aa9a2560d99ad9b6c3661041dbc037c54dd91097d7c213a00fbc
3
+ size 989890728
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5456a56293a4d87b9ca1da95c697dc2448a9536de0b06a23b51a8a911f4005
3
+ size 989890728
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16b2ede240bc885a031675a96c18dc567283301da1a43be840b4d520610a5a5
3
+ size 989890728
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9287e2c58164ae5a37fda5bcf3e456dcf5dd64a7b44d9d8a3cda867038e70667
3
+ size 989890728
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a97a953b6bb30c68be16e4e501095f2dd769b79c0e491a30f14713e08ff39aa
3
+ size 956353248
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a6348e7c9998e1dee95f20972a7740349792e1cc15b3a049cdb221e49f671b
3
+ size 989890728
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a2ded86f3af7096297925bd0ff02c90e51a4fe96cc705eb0249d3a5a6369d7
3
+ size 998279456
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fe5b427470661b70edabd3507941724263c7034202da12365ed8ab1fb872ad8
3
+ size 947956192
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679508443906e3b9c0a558becc8b0759b333aeb8f4edc2316e806cc9bad8963d
3
+ size 989890712
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ce265d9003c82847fa98f8d8573c995924d08c8c706ef6bf7a458279db2bc72
3
+ size 318784416
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 17973272576}, "weight_map": {"lm_head.weight": "model-00001-of-00019.safetensors", "model.embed_tokens.weight": "model-00001-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": null,
55
+ "sp_model_kwargs": {},
56
+ "spaces_between_special_tokens": false,
57
+ "tokenizer_class": "LlamaTokenizer",
58
+ "trust_remote_code": false,
59
+ "unk_token": "<unk>",
60
+ "use_default_system_prompt": true,
61
+ "use_fast": true
62
+ }